generated from mwc/project_argument
1519 lines
135 KiB
Plaintext
1519 lines
135 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "worldwide-blood",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Introduction"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "understanding-numbers",
|
||
"metadata": {},
|
||
"source": [
|
||
"This research examines the relationship between instructors' reported frequencies on focus on developing mathmatical and conceptual models and their reported frequency of using computer-interfacing measurement devices, using course information survey responses that accompany the E-CLASS student data. Understanding this relationship may be able to inform what purposes instructors believe are best suited for using these technologies. Since these are general ratings for the course for the entirety of the semester, it is likely that the granularity is not fine enough to adequately answer this question based on this data alone, but we'll take a look anyways."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "greater-circular",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Overarching Question: How do the reported uses of real-time data visualization devices in physics labs relate to the development of models?"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "43640d34-8f4b-41c3-bdbd-38dbcf51b5d5",
|
||
"metadata": {},
|
||
"source": [
|
||
"The central question is to examine the ways the computer-interfacing measurement devices are used in introductory college physics laboratories, and how they are connected to changes in students' epistemological beliefs and attitudes towards experimentation / laboratory. Computer-interfacing measurement devices are commonly used for collection and visualization of real-time physical data. Most physics instructors accept that these experiences can facilitate the development of both mathematical and conceptual models. However, there have not been many studies which explore the learning processes underlying these assumptions, and learning experiences from the use of these devices in laboratory settings are not well-understood. \n",
|
||
"\n",
|
||
"Additionally, a growing body of research has shown that the roles that learners adopt in physics laboratory learning settings are inequitably distributed by gender, with women undertaking more secretarial and management roles and men undertaking more tinkering and experimenting roles. Although how gender may be connected to learners' experiences using computer-interfacing measurment devices is not well documented, it is possible that similar dynamics plague the use of these technologies, and consequently impact how much learners benefit."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "permanent-pollution",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Data"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "technical-evans",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#Import libraries\n",
|
||
"import pandas as pd\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "overhead-sigma",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"### 💻 FILL IN YOUR DATASET FILE NAME BELOW 💻 ###\n",
|
||
"\n",
|
||
"file_name = \"ECLASS_anon_cis.csv\"\n",
|
||
"dataset_path = data/ECLASS_anon_cis.csv\n",
|
||
"#dataset_path = \"data/\" + file_name\n",
|
||
"\n",
|
||
"df = pd.read_csv(data/ECLASS_anon_cis.csv)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "f1affbce-2a6e-429b-8a58-c337c6fdcd13",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Q5</th>\n",
|
||
" <th>Q52</th>\n",
|
||
" <th>Q53</th>\n",
|
||
" <th>Q18</th>\n",
|
||
" <th>Q27</th>\n",
|
||
" <th>Q6</th>\n",
|
||
" <th>Q11</th>\n",
|
||
" <th>Q19</th>\n",
|
||
" <th>Q20</th>\n",
|
||
" <th>Q15</th>\n",
|
||
" <th>...</th>\n",
|
||
" <th>Q38_4</th>\n",
|
||
" <th>Q41</th>\n",
|
||
" <th>Q42</th>\n",
|
||
" <th>Q43</th>\n",
|
||
" <th>StartDate</th>\n",
|
||
" <th>anon_instructor_id</th>\n",
|
||
" <th>anon_university_id</th>\n",
|
||
" <th>ResponseId</th>\n",
|
||
" <th>pre_survey_id</th>\n",
|
||
" <th>post_survey_id</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>semester</td>\n",
|
||
" <td>Fall</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Calculus-based</td>\n",
|
||
" <td>9/9/2016</td>\n",
|
||
" <td>No incentive</td>\n",
|
||
" <td>55</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>4 year college</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>Never</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>29/07/2016 09:35</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>R_9TQGuSY5m31uCgp</td>\n",
|
||
" <td>eb70O8rWoi7TeEl</td>\n",
|
||
" <td>bdrBNZhS5ctkrtj</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>semester</td>\n",
|
||
" <td>Fall</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Calculus-based</td>\n",
|
||
" <td>9/3/2016</td>\n",
|
||
" <td>Credit for completion (like an assignment)</td>\n",
|
||
" <td>600</td>\n",
|
||
" <td>37</td>\n",
|
||
" <td>PhD granting institution</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>Never</td>\n",
|
||
" <td>6.0</td>\n",
|
||
" <td>12.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>30/07/2016 15:16</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>R_WcbonOUwNhq1aTv</td>\n",
|
||
" <td>enXrvYRTHSwaJiR</td>\n",
|
||
" <td>3I6hLxNFWEUu5Ex</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>semester</td>\n",
|
||
" <td>Fall</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>Beyond the first year lab</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>8/22/2016</td>\n",
|
||
" <td>Credit for completion (like an assignment)</td>\n",
|
||
" <td>23</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>PhD granting institution</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>Always</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>14/08/2016 20:45</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>R_6QckmxZUXlkQ5z3</td>\n",
|
||
" <td>bK2V8FlTDsDGtJX</td>\n",
|
||
" <td>bpVIjAwWGMGtekJ</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>semester</td>\n",
|
||
" <td>Fall</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Calculus-based</td>\n",
|
||
" <td>9/14/2016</td>\n",
|
||
" <td>Credit for completion (like an assignment)</td>\n",
|
||
" <td>25</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>4 year college</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>Sometimes</td>\n",
|
||
" <td>7.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>10.0</td>\n",
|
||
" <td>15/08/2016 08:32</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>R_31hCg7myirwz5YQ</td>\n",
|
||
" <td>bJlVpGxcYoFnxWd</td>\n",
|
||
" <td>3vDaZhGQglbcdiR</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>semester</td>\n",
|
||
" <td>Fall</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Calculus-based</td>\n",
|
||
" <td>9/9/2016</td>\n",
|
||
" <td>No incentive</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>4 year college</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>Never</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>16/08/2016 10:39</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>R_2uUuv0cqKVTrZPd</td>\n",
|
||
" <td>8elF9Rxw2rrXOvP</td>\n",
|
||
" <td>7Vetb0Z6aGRzirH</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>5 rows × 49 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Q5 Q52 Q53 Q18 Q27 \\\n",
|
||
"0 semester Fall NaN First year (introductory) lab Calculus-based \n",
|
||
"1 semester Fall NaN First year (introductory) lab Calculus-based \n",
|
||
"2 semester Fall NaN Beyond the first year lab NaN \n",
|
||
"3 semester Fall NaN First year (introductory) lab Calculus-based \n",
|
||
"4 semester Fall NaN First year (introductory) lab Calculus-based \n",
|
||
"\n",
|
||
" Q6 Q11 Q19 Q20 \\\n",
|
||
"0 9/9/2016 No incentive 55 3 \n",
|
||
"1 9/3/2016 Credit for completion (like an assignment) 600 37 \n",
|
||
"2 8/22/2016 Credit for completion (like an assignment) 23 1 \n",
|
||
"3 9/14/2016 Credit for completion (like an assignment) 25 2 \n",
|
||
"4 9/9/2016 No incentive 40 3 \n",
|
||
"\n",
|
||
" Q15 ... Q38_4 Q41 Q42 Q43 \\\n",
|
||
"0 4 year college ... Never 11.0 11.0 0.0 \n",
|
||
"1 PhD granting institution ... Never 6.0 12.0 0.0 \n",
|
||
"2 PhD granting institution ... Always 1.0 3.0 3.0 \n",
|
||
"3 4 year college ... Sometimes 7.0 3.0 10.0 \n",
|
||
"4 4 year college ... Never 11.0 11.0 0.0 \n",
|
||
"\n",
|
||
" StartDate anon_instructor_id anon_university_id ResponseId \\\n",
|
||
"0 29/07/2016 09:35 0 0 R_9TQGuSY5m31uCgp \n",
|
||
"1 30/07/2016 15:16 1 1 R_WcbonOUwNhq1aTv \n",
|
||
"2 14/08/2016 20:45 2 2 R_6QckmxZUXlkQ5z3 \n",
|
||
"3 15/08/2016 08:32 3 3 R_31hCg7myirwz5YQ \n",
|
||
"4 16/08/2016 10:39 0 0 R_2uUuv0cqKVTrZPd \n",
|
||
"\n",
|
||
" pre_survey_id post_survey_id \n",
|
||
"0 eb70O8rWoi7TeEl bdrBNZhS5ctkrtj \n",
|
||
"1 enXrvYRTHSwaJiR 3I6hLxNFWEUu5Ex \n",
|
||
"2 bK2V8FlTDsDGtJX bpVIjAwWGMGtekJ \n",
|
||
"3 bJlVpGxcYoFnxWd 3vDaZhGQglbcdiR \n",
|
||
"4 8elF9Rxw2rrXOvP 7Vetb0Z6aGRzirH \n",
|
||
"\n",
|
||
"[5 rows x 49 columns]"
|
||
]
|
||
},
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1875294d-24d1-4efa-9042-7d9aa75fe41b",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Data Cleaning"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "44855b13-cfb3-429e-8ddb-d356fd63f3d8",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Q18</th>\n",
|
||
" <th>Q36_1</th>\n",
|
||
" <th>Q36_2</th>\n",
|
||
" <th>Q37_4</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Rarely</td>\n",
|
||
" <td>Rarely</td>\n",
|
||
" <td>Always</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Rarely</td>\n",
|
||
" <td>Rarely</td>\n",
|
||
" <td>Never</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Beyond the first year lab</td>\n",
|
||
" <td>Often</td>\n",
|
||
" <td>Often</td>\n",
|
||
" <td>Often</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Sometimes</td>\n",
|
||
" <td>Often</td>\n",
|
||
" <td>Sometimes</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>Sometimes</td>\n",
|
||
" <td>Rarely</td>\n",
|
||
" <td>Often</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Q18 Q36_1 Q36_2 Q37_4\n",
|
||
"0 First year (introductory) lab Rarely Rarely Always\n",
|
||
"1 First year (introductory) lab Rarely Rarely Never\n",
|
||
"2 Beyond the first year lab Often Often Often\n",
|
||
"3 First year (introductory) lab Sometimes Often Sometimes\n",
|
||
"4 First year (introductory) lab Sometimes Rarely Often"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#new dataframe with columns of interest\n",
|
||
"df_reg_ana = df[['Q18', 'Q36_1', 'Q36_2', 'Q37_4']]\n",
|
||
"df_reg_ana.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "258dd944-c520-4599-b7a7-a5fff19dc728",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:2: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
||
" df_reg_ana['Q36_1'] = df_reg_ana['Q36_1'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:2: SettingWithCopyWarning: \n",
|
||
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
||
"Try using .loc[row_indexer,col_indexer] = value instead\n",
|
||
"\n",
|
||
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
|
||
" df_reg_ana['Q36_1'] = df_reg_ana['Q36_1'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:3: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
||
" df_reg_ana['Q36_2'] = df_reg_ana['Q36_2'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:3: SettingWithCopyWarning: \n",
|
||
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
||
"Try using .loc[row_indexer,col_indexer] = value instead\n",
|
||
"\n",
|
||
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
|
||
" df_reg_ana['Q36_2'] = df_reg_ana['Q36_2'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:4: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
||
" df_reg_ana['Q37_4'] = df_reg_ana['Q37_4'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\2660362453.py:4: SettingWithCopyWarning: \n",
|
||
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
||
"Try using .loc[row_indexer,col_indexer] = value instead\n",
|
||
"\n",
|
||
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
|
||
" df_reg_ana['Q37_4'] = df_reg_ana['Q37_4'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Q18</th>\n",
|
||
" <th>Q36_1</th>\n",
|
||
" <th>Q36_2</th>\n",
|
||
" <th>Q37_4</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>5.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Beyond the first year lab</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Q18 Q36_1 Q36_2 Q37_4\n",
|
||
"0 First year (introductory) lab 2.0 2.0 5.0\n",
|
||
"1 First year (introductory) lab 2.0 2.0 1.0\n",
|
||
"2 Beyond the first year lab 4.0 4.0 4.0\n",
|
||
"3 First year (introductory) lab 3.0 4.0 3.0\n",
|
||
"4 First year (introductory) lab 3.0 2.0 4.0"
|
||
]
|
||
},
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#recode to numerical\n",
|
||
"df_reg_ana['Q36_1'] = df_reg_ana['Q36_1'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"df_reg_ana['Q36_2'] = df_reg_ana['Q36_2'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"df_reg_ana['Q37_4'] = df_reg_ana['Q37_4'].replace({'Never': 1, 'Rarely': 2, 'Sometimes': 3, 'Often': 4, 'Always': 5})\n",
|
||
"df_reg_ana.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"id": "f4c7de1f-dea4-435d-b86a-7a99283919eb",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>level</th>\n",
|
||
" <th>math_models_freq</th>\n",
|
||
" <th>conc_models_freq</th>\n",
|
||
" <th>comp_int_freq</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>5.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Beyond the first year lab</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>First year (introductory) lab</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" level math_models_freq conc_models_freq \\\n",
|
||
"0 First year (introductory) lab 2.0 2.0 \n",
|
||
"1 First year (introductory) lab 2.0 2.0 \n",
|
||
"2 Beyond the first year lab 4.0 4.0 \n",
|
||
"3 First year (introductory) lab 3.0 4.0 \n",
|
||
"4 First year (introductory) lab 3.0 2.0 \n",
|
||
"\n",
|
||
" comp_int_freq \n",
|
||
"0 5.0 \n",
|
||
"1 1.0 \n",
|
||
"2 4.0 \n",
|
||
"3 3.0 \n",
|
||
"4 4.0 "
|
||
]
|
||
},
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#rename columns\n",
|
||
"df_reg_ana = df_reg_ana.rename(columns={'Q18': 'level', 'Q36_1': 'math_models_freq', 'Q36_2': 'conc_models_freq', 'Q37_4': 'comp_int_freq'})\n",
|
||
"df_reg_ana.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"id": "3855ee16-deff-4572-aafe-4bcd8cc32cde",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\stacy\\AppData\\Local\\Temp\\ipykernel_33472\\4007376843.py:2: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
||
" df_reg_ana['level'] = df_reg_ana['level'].replace({'First year (introductory) lab': 1, 'Beyond the first year lab': 0})\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>level</th>\n",
|
||
" <th>math_models_freq</th>\n",
|
||
" <th>conc_models_freq</th>\n",
|
||
" <th>comp_int_freq</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>5.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" level math_models_freq conc_models_freq comp_int_freq\n",
|
||
"0 1 2.0 2.0 5.0\n",
|
||
"1 1 2.0 2.0 1.0\n",
|
||
"2 0 4.0 4.0 4.0\n",
|
||
"3 1 3.0 4.0 3.0\n",
|
||
"4 1 3.0 2.0 4.0"
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#recode level (1 = first year, 0 = beyond first year), calc_or_alg (1 = alg, 0 = calc), inst_type (1 = 2y, 2 = 4y, 3 = PhD granting)\n",
|
||
"df_reg_ana['level'] = df_reg_ana['level'].replace({'First year (introductory) lab': 1, 'Beyond the first year lab': 0})\n",
|
||
"df_reg_ana.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "89122494-60c3-4230-b292-abec915e0f6c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"RangeIndex: 494 entries, 0 to 493\n",
|
||
"Data columns (total 4 columns):\n",
|
||
" # Column Non-Null Count Dtype \n",
|
||
"--- ------ -------------- ----- \n",
|
||
" 0 level 494 non-null int64 \n",
|
||
" 1 math_models_freq 220 non-null float64\n",
|
||
" 2 conc_models_freq 220 non-null float64\n",
|
||
" 3 comp_int_freq 220 non-null float64\n",
|
||
"dtypes: float64(3), int64(1)\n",
|
||
"memory usage: 15.6 KB\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"df_reg_ana.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"id": "475f73b7-f2a7-45b8-9b1d-6389d8291e96",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 220 entries, 0 to 493\n",
|
||
"Data columns (total 4 columns):\n",
|
||
" # Column Non-Null Count Dtype \n",
|
||
"--- ------ -------------- ----- \n",
|
||
" 0 level 220 non-null int64 \n",
|
||
" 1 math_models_freq 220 non-null float64\n",
|
||
" 2 conc_models_freq 220 non-null float64\n",
|
||
" 3 comp_int_freq 220 non-null float64\n",
|
||
"dtypes: float64(3), int64(1)\n",
|
||
"memory usage: 8.6 KB\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#drop missing values\n",
|
||
"df_reg_ana.dropna(inplace=True)\n",
|
||
"df_reg_ana.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"id": "d16c8ce1-a114-46c3-af02-588dca3a7717",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 93 entries, 2 to 483\n",
|
||
"Data columns (total 4 columns):\n",
|
||
" # Column Non-Null Count Dtype \n",
|
||
"--- ------ -------------- ----- \n",
|
||
" 0 level 93 non-null int64 \n",
|
||
" 1 math_models_freq 93 non-null float64\n",
|
||
" 2 conc_models_freq 93 non-null float64\n",
|
||
" 3 comp_int_freq 93 non-null float64\n",
|
||
"dtypes: float64(3), int64(1)\n",
|
||
"memory usage: 3.6 KB\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#drop non-introductory lab courses\n",
|
||
"df_reg_ana = df_reg_ana[df_reg_ana['level'] != 1]\n",
|
||
"df_reg_ana.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "continental-franklin",
|
||
"metadata": {},
|
||
"source": [
|
||
"**Data Overview**\n",
|
||
"\n",
|
||
"The Lewandoski Lab at the University of Colorado Boulder developed and validated the Colorado Learning Attitudes about Science Survey for Experimental Physics (E-CLASS) data collection instrument, and made the dataset publicly accessible and available for additional research use (https://github.com/Lewandowski-Labs-PER/eclass-public/tree/master). This is a well-established Physics Education Research (and Experimental Cold Molecular Physics) lab at an R1 university that has published many studies concerning this and other datasets (https://jila.colorado.edu/lewandowski/publications/scientific/year).\n",
|
||
"\n",
|
||
"The course information survey of the E-CLASS contains 494 responses (rows) from instructors (pre-cleaning), for each class they administered the E-CLASS survey to. Columns which will be important to me are Q18 (level of the course), Q36_1 (Modeling - Develop mathematical models for the system being studied), Q36_2 (Modeling - Develop conceptual models for the system being studied), and Q37_4 (Data analysis and visualization - Use computers to interface with measurement devices)."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e1561989-c267-413a-9510-c003609f4ca5",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Data Distributions"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"id": "7289c0e1-8b9d-4625-aae1-f6abeec4c91d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"level 0.000000\n",
|
||
"math_models_freq -0.025612\n",
|
||
"conc_models_freq 0.019958\n",
|
||
"comp_int_freq 0.416858\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"fischer_kurtosis = df_reg_ana.kurtosis()\n",
|
||
"print(fischer_kurtosis)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"id": "dc1776a6-c39e-41d4-81a1-8e587ce2842d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"level 0.000000\n",
|
||
"math_models_freq -0.202256\n",
|
||
"conc_models_freq -0.407829\n",
|
||
"comp_int_freq -0.648785\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"skewness = df_reg_ana.skew()\n",
|
||
"print(skewness)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "c6c88247-f676-4101-a24a-96b94b21d644",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<Axes: >"
|
||
]
|
||
},
|
||
"execution_count": 21,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_reg_ana['math_models_freq'].hist(bins=5)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "6bf316b7-2d94-445e-9b25-1317cf64fd31",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<Axes: >"
|
||
]
|
||
},
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_reg_ana['conc_models_freq'].hist(bins=5)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"id": "1889f08e-e0cc-4702-9f50-c0ae9dcdf0be",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<Axes: >"
|
||
]
|
||
},
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_reg_ana['comp_int_freq'].hist(bins=5)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "infinite-instrument",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Methods and Results"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"id": "basic-canadian",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#Import any helper files you need here\n",
|
||
"import scipy as sp\n",
|
||
"import statsmodels.miscmodels.ordinal_model as om\n",
|
||
"import seaborn as sns"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "recognized-positive",
|
||
"metadata": {},
|
||
"source": [
|
||
"## First Research Question: Is there a significant relationship between the instructor's rating of mathematical focus frequency in introductory physics labs and the reported frequency of use of computer to interface with measurement devices?"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "graduate-palmer",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Methods"
|
||
]
|
||
},
|
||
{
|
||
"attachments": {},
|
||
"cell_type": "markdown",
|
||
"id": "endless-variation",
|
||
"metadata": {},
|
||
"source": [
|
||
"I will perform an ordinal regression to model this data (using the Statsmodels library), since the numerical values are derived from a Likert scale, and each point on the scale is ordered but the differences between each of the points are not necessarily equal. The distribution of math_models_freq was approximately normal for (based on -1.0 < kurtosis < 1.0 and -0.5 < skewness < 0.5). The distribution of comp_int_freq is slightly left-skewed, so logit transformation will be used. I will present the answer in a scatterplot (using the Seaborn library) and with ordinal regression statistics.\n",
|
||
"\n",
|
||
"I will use math_models_freq and comp_int_freq, which are the instructor-reported frequencies of how often students develop mathematical models for the system being studied and use computers to interface with measurement devices.\r\n",
|
||
")\n",
|
||
"\n",
|
||
"I cleaned the data by first creating a new dataframe, df_reg_ana, containing just the variables of interest, renaming the columns with more descriptive names, recoding the Likert-scale for the reported frequencies (Never, Rarely, Sometimes, Often, Always) to a 5-point numerical scale (1, 2, 3, 4, 5). Then I dropped missing values and kept only the rows for introductory lab coursive"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "portuguese-japan",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Results "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 30,
|
||
"id": "3ccedb81-36bf-4c80-a0f5-5a883662ac8f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"x = df_reg_ana['math_models_freq']\n",
|
||
"y = df_reg_ana['comp_int_freq']\n",
|
||
"sns.scatterplot(x=x, y=y, alpha=0.1)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 31,
|
||
"id": "5f430c68-7a38-4c75-ba09-4ce2e21c27c7",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Optimization terminated successfully.\n",
|
||
" Current function value: 1.278472\n",
|
||
" Iterations: 199\n",
|
||
" Function evaluations: 323\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<table class=\"simpletable\">\n",
|
||
"<caption>OrderedModel Results</caption>\n",
|
||
"<tr>\n",
|
||
" <th>Dep. Variable:</th> <td>comp_int_freq</td> <th> Log-Likelihood: </th> <td> -118.90</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Model:</th> <td>OrderedModel</td> <th> AIC: </th> <td> 247.8</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Method:</th> <td>Maximum Likelihood</td> <th> BIC: </th> <td> 260.5</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Date:</th> <td>Sat, 07 Dec 2024</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Time:</th> <td>16:34:52</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>No. Observations:</th> <td> 93</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Df Residuals:</th> <td> 88</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Df Model:</th> <td> 1</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"</table>\n",
|
||
"<table class=\"simpletable\">\n",
|
||
"<tr>\n",
|
||
" <td></td> <th>coef</th> <th>std err</th> <th>z</th> <th>P>|z|</th> <th>[0.025</th> <th>0.975]</th> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>math_models_freq</th> <td> 0.1932</td> <td> 0.120</td> <td> 1.608</td> <td> 0.108</td> <td> -0.042</td> <td> 0.429</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>1.0/2.0</th> <td> -1.4304</td> <td> 0.472</td> <td> -3.034</td> <td> 0.002</td> <td> -2.355</td> <td> -0.506</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>2.0/3.0</th> <td> -0.3945</td> <td> 0.393</td> <td> -1.005</td> <td> 0.315</td> <td> -1.164</td> <td> 0.375</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>3.0/4.0</th> <td> -0.0038</td> <td> 0.183</td> <td> -0.021</td> <td> 0.984</td> <td> -0.363</td> <td> 0.356</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>4.0/5.0</th> <td> 0.2176</td> <td> 0.129</td> <td> 1.685</td> <td> 0.092</td> <td> -0.036</td> <td> 0.471</td>\n",
|
||
"</tr>\n",
|
||
"</table>"
|
||
],
|
||
"text/latex": [
|
||
"\\begin{center}\n",
|
||
"\\begin{tabular}{lclc}\n",
|
||
"\\toprule\n",
|
||
"\\textbf{Dep. Variable:} & comp\\_int\\_freq & \\textbf{ Log-Likelihood: } & -118.90 \\\\\n",
|
||
"\\textbf{Model:} & OrderedModel & \\textbf{ AIC: } & 247.8 \\\\\n",
|
||
"\\textbf{Method:} & Maximum Likelihood & \\textbf{ BIC: } & 260.5 \\\\\n",
|
||
"\\textbf{Date:} & Sat, 07 Dec 2024 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Time:} & 16:34:52 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{No. Observations:} & 93 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Df Residuals:} & 88 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Df Model:} & 1 & \\textbf{ } & \\\\\n",
|
||
"\\bottomrule\n",
|
||
"\\end{tabular}\n",
|
||
"\\begin{tabular}{lcccccc}\n",
|
||
" & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]} \\\\\n",
|
||
"\\midrule\n",
|
||
"\\textbf{math\\_models\\_freq} & 0.1932 & 0.120 & 1.608 & 0.108 & -0.042 & 0.429 \\\\\n",
|
||
"\\textbf{1.0/2.0} & -1.4304 & 0.472 & -3.034 & 0.002 & -2.355 & -0.506 \\\\\n",
|
||
"\\textbf{2.0/3.0} & -0.3945 & 0.393 & -1.005 & 0.315 & -1.164 & 0.375 \\\\\n",
|
||
"\\textbf{3.0/4.0} & -0.0038 & 0.183 & -0.021 & 0.984 & -0.363 & 0.356 \\\\\n",
|
||
"\\textbf{4.0/5.0} & 0.2176 & 0.129 & 1.685 & 0.092 & -0.036 & 0.471 \\\\\n",
|
||
"\\bottomrule\n",
|
||
"\\end{tabular}\n",
|
||
"%\\caption{OrderedModel Results}\n",
|
||
"\\end{center}"
|
||
],
|
||
"text/plain": [
|
||
"<class 'statsmodels.iolib.summary.Summary'>\n",
|
||
"\"\"\"\n",
|
||
" OrderedModel Results \n",
|
||
"==============================================================================\n",
|
||
"Dep. Variable: comp_int_freq Log-Likelihood: -118.90\n",
|
||
"Model: OrderedModel AIC: 247.8\n",
|
||
"Method: Maximum Likelihood BIC: 260.5\n",
|
||
"Date: Sat, 07 Dec 2024 \n",
|
||
"Time: 16:34:52 \n",
|
||
"No. Observations: 93 \n",
|
||
"Df Residuals: 88 \n",
|
||
"Df Model: 1 \n",
|
||
"====================================================================================\n",
|
||
" coef std err z P>|z| [0.025 0.975]\n",
|
||
"------------------------------------------------------------------------------------\n",
|
||
"math_models_freq 0.1932 0.120 1.608 0.108 -0.042 0.429\n",
|
||
"1.0/2.0 -1.4304 0.472 -3.034 0.002 -2.355 -0.506\n",
|
||
"2.0/3.0 -0.3945 0.393 -1.005 0.315 -1.164 0.375\n",
|
||
"3.0/4.0 -0.0038 0.183 -0.021 0.984 -0.363 0.356\n",
|
||
"4.0/5.0 0.2176 0.129 1.685 0.092 -0.036 0.471\n",
|
||
"====================================================================================\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
"execution_count": 31,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#ordinal regression analysis for math_models_freq and comp_int_freq\n",
|
||
"X = df_reg_ana[\"math_models_freq\"]\n",
|
||
"y = df_reg_ana[\"comp_int_freq\"]\n",
|
||
"model = om.OrderedModel(y, X, dist=\"logit\")\n",
|
||
"result = model.fit()\n",
|
||
"result.summary()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3e554d38-cf35-417b-aee3-5228e3bb048f",
|
||
"metadata": {},
|
||
"source": [
|
||
"The coefficient indicates a 0.1932 unit increase in comp_int_freq for a one unit increase in math_models_freq. The P>|z| values indicate the probability of observing a coefficient as extreme as the calculated coefficient, with the threshhold for significance at alpha. Based on alpha of 0.05, the observed relationship is not statistically significant (P>|z| = 0.108)."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "collectible-puppy",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Second Research Question: Is there a significant relationship between the instructor's rating of conceptual focus frequency in introductory physics labs and the reported frequency of use of computer to interface with measurement devices?"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "demographic-future",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Methods"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "incorporate-roller",
|
||
"metadata": {},
|
||
"source": [
|
||
"I will perform an ordinal regression to model this data (using the Statsmodels library), since the numerical values are derived from a Likert scale, and each point on the scale is ordered but the differences between each of the points are not necessarily equal. The distribution of conc_models_freq was approximately normal for (based on -1.0 < kurtosis < 1.0 and -0.5 < skewness < 0.5). The distribution of comp_int_freq is slightly left-skewed, so logit transformation will be used. I will present the answer in a scatterplot (using the Seaborn library) and with ordinal regression statistics.\n",
|
||
"\n",
|
||
"I will use conc_models_freq and comp_int_freq, which are the instructor-reported frequencies of how often students develop conceptual models for the system being studied and use computers to interface with measurement devices.\n",
|
||
"\n",
|
||
"I cleaned the data by first creating a new dataframe, df_reg_ana, containing just the variables of interest, renaming the columns with more descriptive names, recoding the Likert-scale for the reported frequencies (Never, Rarely, Sometimes, Often, Always) to a 5-point numerical scale (1, 2, 3, 4, 5). Then I dropped missing values and kept only the rows for introductory lab courses."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "juvenile-creation",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Results "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 37,
|
||
"id": "e4496366-5aec-4ab1-8425-a19099a808df",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"x = df_reg_ana['conc_models_freq']\n",
|
||
"y = df_reg_ana['comp_int_freq']\n",
|
||
"sns.scatterplot(x=x, y=y, alpha=0.1)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 38,
|
||
"id": "fc1b7a33-ae18-47e6-8cd2-b67b6169e6d1",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Optimization terminated successfully.\n",
|
||
" Current function value: 1.292302\n",
|
||
" Iterations: 147\n",
|
||
" Function evaluations: 243\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<table class=\"simpletable\">\n",
|
||
"<caption>OrderedModel Results</caption>\n",
|
||
"<tr>\n",
|
||
" <th>Dep. Variable:</th> <td>comp_int_freq</td> <th> Log-Likelihood: </th> <td> -120.18</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Model:</th> <td>OrderedModel</td> <th> AIC: </th> <td> 250.4</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Method:</th> <td>Maximum Likelihood</td> <th> BIC: </th> <td> 263.0</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Date:</th> <td>Sat, 07 Dec 2024</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Time:</th> <td>16:34:53</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>No. Observations:</th> <td> 93</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Df Residuals:</th> <td> 88</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>Df Model:</th> <td> 1</td> <th> </th> <td> </td> \n",
|
||
"</tr>\n",
|
||
"</table>\n",
|
||
"<table class=\"simpletable\">\n",
|
||
"<tr>\n",
|
||
" <td></td> <th>coef</th> <th>std err</th> <th>z</th> <th>P>|z|</th> <th>[0.025</th> <th>0.975]</th> \n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>conc_models_freq</th> <td> 0.0195</td> <td> 0.131</td> <td> 0.149</td> <td> 0.882</td> <td> -0.237</td> <td> 0.276</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>1.0/2.0</th> <td> -1.9548</td> <td> 0.547</td> <td> -3.577</td> <td> 0.000</td> <td> -3.026</td> <td> -0.884</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>2.0/3.0</th> <td> -0.4198</td> <td> 0.395</td> <td> -1.064</td> <td> 0.287</td> <td> -1.193</td> <td> 0.353</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>3.0/4.0</th> <td> -0.0362</td> <td> 0.183</td> <td> -0.198</td> <td> 0.843</td> <td> -0.395</td> <td> 0.323</td>\n",
|
||
"</tr>\n",
|
||
"<tr>\n",
|
||
" <th>4.0/5.0</th> <td> 0.2055</td> <td> 0.129</td> <td> 1.590</td> <td> 0.112</td> <td> -0.048</td> <td> 0.459</td>\n",
|
||
"</tr>\n",
|
||
"</table>"
|
||
],
|
||
"text/latex": [
|
||
"\\begin{center}\n",
|
||
"\\begin{tabular}{lclc}\n",
|
||
"\\toprule\n",
|
||
"\\textbf{Dep. Variable:} & comp\\_int\\_freq & \\textbf{ Log-Likelihood: } & -120.18 \\\\\n",
|
||
"\\textbf{Model:} & OrderedModel & \\textbf{ AIC: } & 250.4 \\\\\n",
|
||
"\\textbf{Method:} & Maximum Likelihood & \\textbf{ BIC: } & 263.0 \\\\\n",
|
||
"\\textbf{Date:} & Sat, 07 Dec 2024 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Time:} & 16:34:53 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{No. Observations:} & 93 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Df Residuals:} & 88 & \\textbf{ } & \\\\\n",
|
||
"\\textbf{Df Model:} & 1 & \\textbf{ } & \\\\\n",
|
||
"\\bottomrule\n",
|
||
"\\end{tabular}\n",
|
||
"\\begin{tabular}{lcccccc}\n",
|
||
" & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]} \\\\\n",
|
||
"\\midrule\n",
|
||
"\\textbf{conc\\_models\\_freq} & 0.0195 & 0.131 & 0.149 & 0.882 & -0.237 & 0.276 \\\\\n",
|
||
"\\textbf{1.0/2.0} & -1.9548 & 0.547 & -3.577 & 0.000 & -3.026 & -0.884 \\\\\n",
|
||
"\\textbf{2.0/3.0} & -0.4198 & 0.395 & -1.064 & 0.287 & -1.193 & 0.353 \\\\\n",
|
||
"\\textbf{3.0/4.0} & -0.0362 & 0.183 & -0.198 & 0.843 & -0.395 & 0.323 \\\\\n",
|
||
"\\textbf{4.0/5.0} & 0.2055 & 0.129 & 1.590 & 0.112 & -0.048 & 0.459 \\\\\n",
|
||
"\\bottomrule\n",
|
||
"\\end{tabular}\n",
|
||
"%\\caption{OrderedModel Results}\n",
|
||
"\\end{center}"
|
||
],
|
||
"text/plain": [
|
||
"<class 'statsmodels.iolib.summary.Summary'>\n",
|
||
"\"\"\"\n",
|
||
" OrderedModel Results \n",
|
||
"==============================================================================\n",
|
||
"Dep. Variable: comp_int_freq Log-Likelihood: -120.18\n",
|
||
"Model: OrderedModel AIC: 250.4\n",
|
||
"Method: Maximum Likelihood BIC: 263.0\n",
|
||
"Date: Sat, 07 Dec 2024 \n",
|
||
"Time: 16:34:53 \n",
|
||
"No. Observations: 93 \n",
|
||
"Df Residuals: 88 \n",
|
||
"Df Model: 1 \n",
|
||
"====================================================================================\n",
|
||
" coef std err z P>|z| [0.025 0.975]\n",
|
||
"------------------------------------------------------------------------------------\n",
|
||
"conc_models_freq 0.0195 0.131 0.149 0.882 -0.237 0.276\n",
|
||
"1.0/2.0 -1.9548 0.547 -3.577 0.000 -3.026 -0.884\n",
|
||
"2.0/3.0 -0.4198 0.395 -1.064 0.287 -1.193 0.353\n",
|
||
"3.0/4.0 -0.0362 0.183 -0.198 0.843 -0.395 0.323\n",
|
||
"4.0/5.0 0.2055 0.129 1.590 0.112 -0.048 0.459\n",
|
||
"====================================================================================\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
"execution_count": 38,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#ordinal regression analysis for conc_models_freq and comp_int_freq\n",
|
||
"X = df_reg_ana[\"conc_models_freq\"]\n",
|
||
"y = df_reg_ana[\"comp_int_freq\"]\n",
|
||
"model = om.OrderedModel(y, X, dist=\"logit\")\n",
|
||
"result = model.fit()\n",
|
||
"result.summary()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3fc177af-cd92-494a-b3e0-3bf5d7e7f91b",
|
||
"metadata": {},
|
||
"source": [
|
||
"The coefficient indicates a 0.0195 unit increase in comp_int_freq for a one unit increase in conc_models_freq. The P>|z| values indicate the probability of observing a coefficient as extreme as the calculated coefficient, with the threshhold for significance at alpha. Based on alpha of 0.05, the observed relationship is not statistically significant (P>|z| = 0.882)."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "infectious-symbol",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Discussion"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "furnished-camping",
|
||
"metadata": {
|
||
"code_folding": []
|
||
},
|
||
"source": [
|
||
"## Considerations"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "bearing-stadium",
|
||
"metadata": {},
|
||
"source": [
|
||
"These results indicate that instructor rated frequency of developing neither mathematical nor conceptual models in lab are strong or significant predictors of their use of computers to interface with data collection devices. The research question is probably better answered through interviews (qualitative) or observation or document analysis of laboratory manuals (qualitative or quantitative).\n",
|
||
"\n",
|
||
"The dataset has some limitations, including the construction and validation of the course information survey, which was not validated as part of the student survey for E-CLASS. While some of the items are objective, such as the level and math-basis of the course, the Likert scale used to assess frequency of laboratory instructional choices should have been validated. After cleaning the dataset and omitting rows with missing values, there were only 93 entries included in the analysis.\n",
|
||
"\n",
|
||
"Self-selection bias is a flaw of this data, as the survey was administered to classes based on the instructor choosing to do so."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "beneficial-invasion",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Summary"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "about-raise",
|
||
"metadata": {},
|
||
"source": [
|
||
"I think the results made sense, based on the way the data was collected. I hadn't used this statistical model before (so my execution could also be flawed), and previously I've mainly used linear regression for analysis of interval or continuous data. However, although sometimes linear regression is used for Likert scale data (as many commercial statistical softwares do not have ordinal regression capabilities), it seemed like a better choice to use the ordinal regression model. \n",
|
||
"\n",
|
||
"Generally, I'm not a huge fan of Likert scale surveys. I would probably not use one in my own research. However, I think it was a good experience to look at this dataset more deeply and do some analysis with it. I'm looking the other side of the data (the student responses to the epistemological items) in another class, and that has been validated so maybe there will be something there."
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"jupytext": {
|
||
"cell_metadata_json": true,
|
||
"text_representation": {
|
||
"extension": ".Rmd",
|
||
"format_name": "rmarkdown",
|
||
"format_version": "1.2",
|
||
"jupytext_version": "1.9.1"
|
||
}
|
||
},
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.12.4"
|
||
},
|
||
"toc": {
|
||
"base_numbering": 1,
|
||
"nav_menu": {},
|
||
"number_sections": false,
|
||
"sideBar": true,
|
||
"skip_h1_title": false,
|
||
"title_cell": "Table of Contents",
|
||
"title_sidebar": "Contents",
|
||
"toc_cell": false,
|
||
"toc_position": {},
|
||
"toc_section_display": true,
|
||
"toc_window_display": false
|
||
},
|
||
"varInspector": {
|
||
"cols": {
|
||
"lenName": 16,
|
||
"lenType": 16,
|
||
"lenVar": 40
|
||
},
|
||
"kernels_config": {
|
||
"python": {
|
||
"delete_cmd_postfix": "",
|
||
"delete_cmd_prefix": "del ",
|
||
"library": "var_list.py",
|
||
"varRefreshCmd": "print(var_dic_list())"
|
||
},
|
||
"r": {
|
||
"delete_cmd_postfix": ") ",
|
||
"delete_cmd_prefix": "rm(",
|
||
"library": "var_list.r",
|
||
"varRefreshCmd": "cat(var_dic_list()) "
|
||
}
|
||
},
|
||
"types_to_exclude": [
|
||
"module",
|
||
"function",
|
||
"builtin_function_or_method",
|
||
"instance",
|
||
"_Feature"
|
||
],
|
||
"window_display": false
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|